# yueliu1999/Awesome-Jailbreak-on-LLMs

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

Repository: https://github.com/yueliu1999/Awesome-Jailbreak-on-LLMs
Canonical: https://ross.abutalabs.com/products/awesome-jailbreak-on-llms
License: MIT
License Family: permissive
Topics: ai, jailbreak, llm, llms, privacy, safety, security, vlm, vlms
Last push: 2026-08-10T16:54:43+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 56
- inputs: {"age_days": 797, "days_push": 23, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1602, forks 126 (observed 2026-08-28T04:05:09.789551+00:00)

## What it is
A curated awesome-list collecting state-of-the-art jailbreak methods on large language models, including papers, code, datasets, evaluations, and analyses. It covers jailbreak attacks (black-box, white-box, multi-turn, multi-modal, on LRMs and RAG-based LLMs) and defenses such as guard models and moderation APIs.

## Use cases
- find recent papers on LLM jailbreak attacks
- research red-teaming techniques for large language models
- find datasets for evaluating LLM safety
- compare jailbreak defense methods and guard models
- survey multi-modal jailbreak attacks on vision-language models
- find open-source implementations of jailbreak attacks

## When to choose
- you are researching LLM safety, adversarial attacks, or guardrails
- you need a curated starting point for jailbreak literature and code
- you want to benchmark or evaluate LLM robustness against attacks

## When to avoid
- you need a production tool or library rather than a paper collection
- you want a general LLM safety resource not focused on jailbreaks
- you need a maintained software package with APIs

## Facets
- artifact type: learning-resource
- maturity: active
- function: security, nlp, machine-learning
- domain: large-language-models, security, artificial-intelligence, awesome-lists
- platform: cross-platform
- tags: jailbreak, llm-safety, awesome-list, red-teaming, adversarial-attacks, guardrails, vlm

## Member repositories
- yueliu1999/Awesome-Jailbreak-on-LLMs (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:09.789551+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:52:38.694693+00:00, confidence not recorded.
  - readme: https://github.com/yueliu1999/Awesome-Jailbreak-on-LLMs (fetched 2026-08-28T04:05:09.789551+00:00, sha 64bf3c9a58b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.